From 3054235dc09b1667c5c897f976eafa18845283e1 Mon Sep 17 00:00:00 2001 From: Cj Malone Date: Thu, 26 Jan 2023 16:10:57 +0000 Subject: [PATCH] Don't check robotstxt for local files --- scrapy/downloadermiddlewares/robotstxt.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/scrapy/downloadermiddlewares/robotstxt.py b/scrapy/downloadermiddlewares/robotstxt.py index 326c35290..8e9beeeef 100644 --- a/scrapy/downloadermiddlewares/robotstxt.py +++ b/scrapy/downloadermiddlewares/robotstxt.py @@ -38,6 +38,8 @@ class RobotsTxtMiddleware: def process_request(self, request, spider): if request.meta.get("dont_obey_robotstxt"): return + if request.url.startswith("data:") or request.url.startswith("file:"): + return d = maybeDeferred(self.robot_parser, request, spider) d.addCallback(self.process_request_2, request, spider) return d